Yiwei Lu

I am a first year Ph.D. student in the David R. Cheriton School of Computer Science at the University of Waterloo, where I am supervised by Prof. Yaoliang Yu and Prof. Sun Sun. I am also a student affiliate of the Vector Instituite.

Previously, I have completed my M.Sc. in Computer Science at the University of Manitoba, where I was advised by Prof. Yang Wang. I did my bachelors at the University of Electronic Science and Technology of China. I was also an exchange student at UC Santa Barbara and an intern at Huawei Chengdu Research Center.

Email  /  CV  /  Google Scholar  /  Github  /  LinkedIn

  New! Feb 2022:I am joining Huawei Noah's Ark Lab in Montreal as an Intern.
  New! Nov 2021: One paper accepted as an oral to NeurIPS 2021 workshop on self-supervised learning.
  Feb 2021:One paper accepted to IEEE TMM.
  January 2021: I am joining National Research Council of Canada as an Intern
  September 2020: I am serving as a reviewer in AAAI 2021
  August 2020: I am presenting 1 paper in ECCV 2020
  August 2020: I am joining University of Waterloo and Vector Instituite as a Ph.D. student

I'm interested in machine learning and its application on computer vision. I am particularly interested in self-supervised learning and adversarial machine learning.

We propose a general and novel loss function on contrastive learning based on f-mutual information.

We propose a new problem called unlabeled scene adaptive crowd counting.

We propose a more realistic problem setting for anomaly detection in surveillance videos and solve it using a meta-learning based algorithm.

We propose a structure learning framework that retains the pairwise similarities between the data points.

We propose a novel sequential generative model based on variational autoencoder (VAE) for future frame prediction with convolutional LSTM (ConvLSTM).

We propose a novel similarity learning framework by minimizing the reconstruction error of kernel matrices, rather than the reconstruction error of original data adopted by existing work.

We propose a ConvLSTM-based model to perform semantic segmentation on compressed videos directly. This significantly speed up the training and test speed.

Anomaly Detection in Surveillance Videos using Deep Learning - Yiwei Lu, M.Sc.thesis, Department of Computer Science, University of Manitoba, June 2020.

Credits to Jon Barron for the website design.